INDEX

Explanations

differences or contradictions in statements

oai_token-act-pair · gpt-3.5-turbo

phrases related to conversation and communication dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

culus

-0.98

atri

-0.82

cephal

-0.76

ahime

-0.76

ggle

-0.74

taboola

-0.74

anus

-0.72

ãĥī

-0.71

tnc

-0.71

ummer

-0.68

POSITIVE LOGITS

 THEN

0.97

 preferably

0.93

 then

0.89

 verbally

0.87

 paraph

0.86

 retweet

0.80

 phrases

0.79

 concise

0.79

 criticize

0.79

 orally

0.78

Activations Density 0.625%

differences or contradictions in statements

phrases related to conversation and communication dynamics

No Comments

No Known Activations