INDEX

Explanations

words related to a specific name or entity in various contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of a specific individual named Juanita

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

enegger

-0.80

dropping

-0.76

roads

-0.73

shows

-0.72

pelled

-0.71

paren

-0.71

edge

-0.71

STON

-0.69

ullivan

-0.67

roups

-0.67

POSITIVE LOGITS

BILITY

0.86

Ã±

0.81

 Gupta

0.80

iba

0.80

 Scotia

0.79

Lum

0.74

ibu

0.74

 Suarez

0.72

ichi

0.71

vel

0.71

Activations Density 0.026%

words related to a specific name or entity in various contexts

mentions of a specific individual named Juanita

No Comments

No Known Activations