INDEX

Explanations

references to specific names or identities, particularly ones related to scandals or controversies

oai_token-act-pair · gpt-3.5-turbo

instances of a specific name or term repeated in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gie

-0.71

ãģŁ

-0.68

FUL

-0.67

 Democr

-0.66

fully

-0.66

 Valent

-0.66

Buc

-0.65

ger

-0.65

swick

-0.64

fulness

-0.64

POSITIVE LOGITS

olitics

1.25

olicy

1.02

odcast

1.01

acing

0.99

etition

0.94

roximately

0.93

roxy

0.93

rison

0.92

aic

0.91

acus

0.90

Activations Density 0.027%

references to specific names or identities, particularly ones related to scandals or controversies

instances of a specific name or term repeated in various contexts

No Comments

No Known Activations