INDEX

Explanations

adjectives related to exploration and legal terms

oai_token-act-pair · gpt-3.5-turbo

terms related to exploratory and evaluative processes

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

frey

-0.77

aret

-0.73

 Leilan

-0.72

igrate

-0.71

igon

-0.69

istor

-0.69

ned

-0.69

generic

-0.68

 Brist

-0.68

 Tornado

-0.68

POSITIVE LOGITS

 sidx

0.88

atory

0.88

 Measures

0.76

ItemTracker

0.73

 enqu

0.72

 measures

0.72

 pronoun

0.70

TY

0.70

 veto

0.68

itative

0.67

Activations Density 0.049%

adjectives related to exploration and legal terms

terms related to exploratory and evaluative processes

No Comments

No Known Activations