INDEX

Explanations

instances of "into" followed by relevant contextual phrases, often related to a progression or transition in an event or situation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

instances of the word "into" followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ©Ł

-0.79

founded

-0.70

found

-0.69

ailable

-0.69

aires

-0.66

ice

-0.64

ickets

-0.64

fa

-0.62

ulla

-0.62

dust

-0.62

POSITIVE LOGITS

 adulthood

0.85

imester

0.85

 season

0.81

phabet

0.75

 recovery

0.75

 Thanksgiving

0.73

 rollout

0.71

 preparations

0.70

 adolescence

0.70

 semester

0.70

Activations Density 0.139%

instances of "into" followed by relevant contextual phrases, often related to a progression or transition in an event or situation

instances of the word "into" followed by a numerical value

No Comments

No Known Activations

instances of "into" followed by relevant contextual phrases, often related to a progression or transition in an event or situation

instances of the word "into" followed by a numerical value

No Comments

No Known Activations