INDEX

Explanations

phrases related to discussing or describing ways or methods

oai_token-act-pair · gpt-3.5-turbo

phrases that describe methods or approaches to situations

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

usters

-0.96

uster

-0.90

 livest

-0.78

encer

-0.73

lict

-0.72

 sugg

-0.70

igh

-0.70

ĸļ

-0.69

acca

-0.68

incinn

-0.67

POSITIVE LOGITS

fare

1.04

ward

0.93

finding

0.88

point

0.81

bill

0.75

sey

0.72

points

0.72

 Drawn

0.72

lay

0.70

 THEY

0.65

Activations Density 0.034%

phrases related to discussing or describing ways or methods

phrases that describe methods or approaches to situations

No Comments

No Known Activations