INDEX

Explanations

phrases related to actions and processes

oai_token-act-pair · gpt-3.5-turbo

phrases that describe actions or conditions related to observation and interpretation

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

paio

-0.75

ajo

-0.73

iland

-0.68

awar

-0.66

 Vaughan

-0.65

oice

-0.64

Lev

-0.63

hov

-0.61

ahoo

-0.60

mar

-0.60

POSITIVE LOGITS

 properly

0.87

 individually

0.72

 correctly

0.65

cule

0.64

 scientifically

0.63

 separately

0.61

 Higher

0.61

});

0.61

 geographically

0.60

 sufficiently

0.60

Activations Density 0.079%

phrases related to actions and processes

phrases that describe actions or conditions related to observation and interpretation

No Comments

No Known Activations