INDEX

Explanations

words related to conclusions or finality

oai_token-act-pair · gpt-3.5-turbo

phrases indicating outcomes or conclusions

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

itsch

-0.77

htaking

-0.68

esome

-0.66

hee

-0.65

esis

-0.65

iets

-0.62

æ©Ł

-0.62

 principals

-0.59

thouse

-0.59

king

-0.59

POSITIVE LOGITS

angering

1.25

owment

0.98

ocrin

0.94

angered

0.92

 abruptly

0.90

ocrine

0.88

angers

0.85

 prematurely

0.84

 tragically

0.82

orses

0.77

Activations Density 0.038%

words related to conclusions or finality

phrases indicating outcomes or conclusions

No Comments

No Known Activations