INDEX

Explanations

phrases indicating the absence of something or someone

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the cessation of previous actions or states

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

emet

-0.74

stood

-0.74

maximum

-0.73

arity

-0.73

iot

-0.73

ffe

-0.73

ouri

-0.72

erest

-0.72

romy

-0.72

odan

-0.71

POSITIVE LOGITS

ado

0.85

thin

0.73

iatus

0.71

 than

0.71

THING

0.70

adays

0.70

 antioxid

0.69

 pregn

0.66

:(

0.66

 anymore

0.64

Activations Density 0.009%

phrases indicating the absence of something or someone

phrases indicating the cessation of previous actions or states

No Comments

No Known Activations