INDEX

Explanations

occurrences of the word 'starting' in the text

oai_token-act-pair · gpt-3.5-turbo

terms related to roles in sports or theatrical productions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

utics

-0.98

atism

-0.87

akespeare

-0.82

 Retrieved

-0.78

alach

-0.78

ascript

-0.77

ynthesis

-0.77

utical

-0.76

atche

-0.75

olia

-0.74

POSITIVE LOGITS

 trio

1.03

 group

0.94

 lineup

0.88

 line

0.85

 ones

0.84

leg

0.82

 party

0.82

 panel

0.81

most

0.81

 challenger

0.79

Activations Density 0.193%

occurrences of the word 'starting' in the text

terms related to roles in sports or theatrical productions

No Comments

No Known Activations