INDEX

Explanations

mentions of the word "Got" with high activation

oai_token-act-pair · gpt-3.5-turbo

references to a specific subject related to "Got."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ently

-0.73

externalActionCode

-0.66

SPONSORED

-0.64

imposed

-0.62

ptive

-0.61

EStreamFrame

-0.61

 comfort

-0.60

inges

-0.59

oided

-0.58

ingly

-0.58

POSITIVE LOGITS

ãĤ¤ãĥĪ

0.84

nesday

0.84

heimer

0.70

alia

0.69

 Parenthood

0.69

 Alive

0.67

ãĥĥãĥĪ

0.67

holm

0.66

 Lives

0.65

mary

0.65

Activations Density 0.109%

mentions of the word "Got" with high activation

references to a specific subject related to "Got."

No Comments

No Known Activations