INDEX

Explanations

words related to fragmentation or breaking apart

oai_token-act-pair · gpt-3.5-turbo

terms related to fragmentation

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

swick

-0.86

Chel

-0.73

hiro

-0.68

orthy

-0.67

hatt

-0.66

Reviewer

-0.65

kins

-0.64

tower

-0.64

reon

-0.62

iard

-0.61

POSITIVE LOGITS

mentation

0.96

mented

0.87

Berry

0.80

bite

0.80

ment

0.79

 frag

0.77

rative

0.77

 grenades

0.75

 Frag

0.74

mental

0.74

Activations Density 0.055%

words related to fragmentation or breaking apart

terms related to fragmentation

No Comments

No Known Activations