INDEX

Explanations

phrases indicating evidence or illustration of a point

oai_token-act-pair · gpt-3.5-turbo

terms that indicate evidence or illustration of concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

hov

-0.76

query

-0.73

scribe

-0.72

adra

-0.71

nel

-0.69

pour

-0.68

frame

-0.67

quer

-0.67

ading

-0.66

 ILCS

-0.64

POSITIVE LOGITS

umerable

0.89

 illustrated

0.83

 evidenced

0.82

ocument

0.77

imentary

0.76

 shown

0.74

ĸļ

0.73

sbm

0.73

 displays

0.72

shown

0.70

Activations Density 0.009%

phrases indicating evidence or illustration of a point

terms that indicate evidence or illustration of concepts

No Comments

No Known Activations