INDEX

Explanations

words related to specific names or entities, particularly those starting with "Arne"

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "ne" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

rador

-0.94

hips

-0.81

rament

-0.81

inarily

-0.80

enhagen

-0.78

rican

-0.75

 glim

-0.75

displayText

-0.75

redited

-0.75

orsi

-0.71

POSITIVE LOGITS

arest

1.05

zel

0.94

verend

0.87

braska

0.86

jad

0.86

gan

0.84

cht

0.84

cker

0.83

lde

0.83

 Hath

0.82

Activations Density 0.016%

words related to specific names or entities, particularly those starting with "Arne"

the presence of the word "ne" in various contexts

No Comments

No Known Activations