INDEX

Explanations

words related to spreading, overwhelming, or saturating something

oai_token-act-pair · gpt-3.5-turbo

verbs and terms associated with overwhelming presence or influence

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

peer

-0.80

IFF

-0.73

stop

-0.72

neg

-0.72

uber

-0.72

iggurat

-0.70

 srfAttach

-0.69

hene

-0.68

raq

-0.68

err

-0.68

POSITIVE LOGITS

uzz

0.87

 inbox

0.83

issance

0.76

ciating

0.76

iously

0.76

 dots

0.73

 waters

0.72

agues

0.71

 adul

0.70

 coats

0.69

Activations Density 0.107%

words related to spreading, overwhelming, or saturating something

verbs and terms associated with overwhelming presence or influence

No Comments

No Known Activations