INDEX

Explanations

phrases related to changes or transitions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating current actions or transitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

LOCK

-0.67

 Logged

-0.62

ANA

-0.61

 bodily

-0.60

 encyclopedia

-0.59

 Gallery

-0.56

 worthy

-0.55

 deserve

-0.55

chy

-0.54

 Mystic

-0.54

POSITIVE LOGITS

uddenly

1.02

instead

0.92

iott

0.82

 suddenly

0.77

 reversed

0.76

emer

0.72

today

0.71

Instead

0.67

 shifted

0.67

rosso

0.66

Activations Density 0.989%

phrases related to changes or transitions

phrases indicating current actions or transitions

No Comments

No Known Activations