INDEX

Explanations

mentions of specific segments in different contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "segment" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

CHA

-0.71

 opio

-0.68

 lett

-0.67

ullivan

-0.62

 Roller

-0.61

 brink

-0.60

Jr

-0.60

stroke

-0.59

dra

-0.59

rises

-0.57

POSITIVE LOGITS

ation

1.17

ated

1.04

ed

1.03

naire

0.94

meal

0.93

ational

0.87

als

0.87

ary

0.86

arily

0.84

eston

0.83

Activations Density 0.047%

mentions of specific segments in different contexts

occurrences of the word "segment" and its variations

No Comments

No Known Activations