INDEX

Explanations

the word "Fri" with varying numeric values indicating different levels of relevance or importance

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Fri"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

lessly

-0.86

ilater

-0.75

Trend

-0.71

lane

-0.67

abwe

-0.67

ATES

-0.66

schild

-0.65

myra

-0.65

popular

-0.65

official

-0.64

POSITIVE LOGITS

urnal

1.01

Fri

0.87

Fri

0.86

zzle

0.82

ezvous

0.81

fri

0.79

Thu

0.76

cipled

0.75

emate

0.75

Tue

0.75

Activations Density 0.007%

the word "Fri" with varying numeric values indicating different levels of relevance or importance

instances of the word "Fri"

No Comments

No Known Activations