INDEX

Explanations

This neuron is looking for words related to emphasis on specific elements or comparisons

oai_token-act-pair · gpt-3.5-turbo

frequently mentioned subjects and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

£ı

-0.89

Ń·

-0.86

nsic

-0.82

swick

-0.80

«ĺ

-0.76

allery

-0.74

auc

-0.74

 CrossRef

-0.72

isky

-0.72

LEASE

-0.70

POSITIVE LOGITS

 Ascension

0.63

 breaths

0.60

 Summers

0.59

 Sandwich

0.59

 wings

0.58

 weap

0.58

 awaited

0.58

 compos

0.58

athe

0.58

 seeker

0.57

Activations Density 0.121%

This neuron is looking for words related to emphasis on specific elements or comparisons

frequently mentioned subjects and their attributes

No Comments

No Known Activations