INDEX

Explanations

instances of the word "see."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "see" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

adding

-0.66

EStreamFrame

-0.66

 suscept

-0.65

stead

-0.63

ieri

-0.62

 reign

-0.61

currency

-0.59

angan

-0.59

orst

-0.59

inion

-0.59

POSITIVE LOGITS

dust

1.09

lights

0.89

 visions

0.82

 daylight

0.81

eye

0.81

adow

0.80

 faces

0.77

 afar

0.77

real

0.76

awed

0.75

Activations Density 0.107%

instances of the word "see."

occurrences of the word "see" and its variations

No Comments

No Known Activations