INDEX

Explanations

verbs related to involvement or immersion

oai_token-act-pair · gpt-3.5-turbo

words associated with conflict and entanglement in various contexts

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

eways

-0.65

iets

-0.61

apes

-0.60

 Chim

-0.58

jab

-0.58

 Gemini

-0.58

eway

-0.57

 snipp

-0.57

Ļ

-0.56

behavior

-0.56

POSITIVE LOGITS

htaking

0.88

 therein

0.81

deep

0.77

ined

0.76

illac

0.72

oided

0.72

igating

0.71

ipel

0.70

 GDDR

0.70

sea

0.69

Activations Density 0.144%

verbs related to involvement or immersion

words associated with conflict and entanglement in various contexts

No Comments

No Known Activations