INDEX

Explanations

references to interactions with strangers, especially in a helpful or considerate context

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "stranger" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

rity

-0.85

rates

-0.82

erb

-0.73

iox

-0.72

REE

-0.71

rix

-0.71

inion

-0.70

vez

-0.70

odium

-0.68

prus

-0.68

POSITIVE LOGITS

liness

0.91

ishly

0.79

hood

0.78

 grop

0.78

 flung

0.76

 strangers

0.75

 bitten

0.74

 stranger

0.73

worldly

0.71

 whom

0.68

Activations Density 0.022%

references to interactions with strangers, especially in a helpful or considerate context

occurrences of the word "stranger" in various contexts

No Comments

No Known Activations