INDEX

Explanations

text related to serious matters or issues

oai_token-act-pair · gpt-3.5-turbo

instances of the word "serious."

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

atu

-0.83

tein

-0.77

eez

-0.77

ucky

-0.75

wright

-0.73

 Tycoon

-0.72

enaries

-0.72

orius

-0.66

hops

-0.65

orious

-0.65

POSITIVE LOGITS

lly

0.95

serious

0.92

 serious

0.87

 dent

0.80

 enough

0.79

nces

0.77

mond

0.75

itar

0.75

enough

0.74

 consideration

0.74

Activations Density 0.023%

text related to serious matters or issues

instances of the word "serious."

No Comments

No Known Activations