INDEX

Explanations

quotes spoken by individuals

oai_token-act-pair · gpt-3.5-turbo

instances of the word "told" in reported speech

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 ILCS

-0.77

reci

-0.71

racted

-0.70

icons

-0.68

spir

-0.67

untled

-0.65

MIT

-0.64

immune

-0.63

tan

-0.61

osterone

-0.61

POSITIVE LOGITS

tale

0.98

ingly

0.83

him

0.77

me

0.76

tell

0.76

IPS

0.76

 reporters

0.75

us

0.75

eret

0.74

mares

0.73

Activations Density 0.060%

quotes spoken by individuals

instances of the word "told" in reported speech

No Comments

No Known Activations