INDEX

Explanations

the mention of film directors

oai_token-act-pair · gpt-3.5-turbo

references to directors and writers in films or shows

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

bia

-0.91

olate

-0.86

vernment

-0.84

externalActionCode

-0.82

cair

-0.81

iscal

-0.80

phrine

-0.79

Interstitial

-0.77

nels

-0.76

merce

-0.76

POSITIVE LOGITS

 Jeffrey

0.93

 Kenneth

0.90

 Josh

0.87

 Wizards

0.87

 Jonathan

0.86

Kev

0.86

 Jeff

0.85

 Aaron

0.85

 Judd

0.84

 Robert

0.83

Activations Density 0.087%

the mention of film directors

references to directors and writers in films or shows

No Comments

No Known Activations