INDEX

Explanations

comparative statements

oai_token-act-pair · gpt-3.5-turbo

statements about fairness and comparisons

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

acho

-0.67

 Femin

-0.66

holm

-0.65

\":

-0.62

achev

-0.61

ourning

-0.61

chieve

-0.60

acha

-0.60

illion

-0.59

ilings

-0.59

POSITIVE LOGITS

 accordingly

0.71

 moot

0.66

eming

0.64

 unus

0.61

="/

0.59

=~

0.58

=#

0.57

untarily

0.55

IOR

0.55

llular

0.55

Activations Density 0.850%

comparative statements

statements about fairness and comparisons

No Comments

No Known Activations