INDEX

Explanations

words related to forceful actions or movements

oai_token-act-pair · gpt-3.5-turbo

words related to forceful actions or changes

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

keeper

-0.90

Trust

-0.73

displayText

-0.70

andro

-0.70

externalActionCode

-0.68

azel

-0.68

keepers

-0.67

Occ

-0.66

osuke

-0.63

Hug

-0.63

POSITIVE LOGITS

icularly

0.84

rolet

0.84

lishes

0.82

ments

0.81

ting

0.79

nesday

0.78

 thrust

0.77

throw

0.77

 spear

0.73

sonian

0.73

Activations Density 0.071%

words related to forceful actions or movements

words related to forceful actions or changes

No Comments

No Known Activations