INDEX

Explanations

keywords related to acceptance or feelings within various contexts

oai_token-act-pair · gpt-3.5-turbo

terms associated with acceptance and emotional responses to societal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ouf

-0.67

owitz

-0.67

onies

-0.66

claimer

-0.62

orio

-0.61

istries

-0.61

 Bravo

-0.59

 Shining

-0.59

odore

-0.58

sit

-0.57

POSITIVE LOGITS

 universally

0.87

 unanimously

0.81

ĸļ

0.75

 psychiat

0.75

ynamic

0.74

 inconsist

0.74

by

0.73

nergy

0.69

 everywhere

0.69

ãĥ¼ãĥĨ

0.68

Activations Density 0.216%

keywords related to acceptance or feelings within various contexts

terms associated with acceptance and emotional responses to societal issues

No Comments

No Known Activations