INDEX

Explanations

Specific mentions or occurrences of the word "Allegations"

oai_token-act-pair · gpt-3.5-turbo

references to allegations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

âķĲâķĲ

-0.72

OPLE

-0.72

flix

-0.69

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

-0.68

ORGE

-0.67

nown

-0.67

amsung

-0.66

 Wilde

-0.66

 Cage

-0.64

Interstitial

-0.63

POSITIVE LOGITS

edly

1.21

heny

1.17

iance

1.09

 Alleg

1.07

ations

0.89

iances

0.83

orical

0.83

arie

0.83

alg

0.81

ict

0.80

Activations Density 0.009%

Specific mentions or occurrences of the word "Allegations"

references to allegations

No Comments

No Known Activations