INDEX

Explanations

names involving communications and media

oai_token-act-pair · gpt-3.5-turbo

references to various forms of media and their coverage in relation to events or issues

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cop

-0.64

 positional

-0.62

 partial

-0.61

 Construction

-0.59

sin

-0.59

tein

-0.58

 contraction

-0.57

 rebound

-0.55

ometric

-0.55

 Integrity

-0.55

POSITIVE LOGITS

 circles

0.93

lance

0.80

rooms

0.80

waves

0.74

Nation

0.72

geist

0.72

 pundits

0.72

agents

0.71

fters

0.70

ourt

0.70

Activations Density 0.300%

names involving communications and media

references to various forms of media and their coverage in relation to events or issues

No Comments

No Known Activations