INDEX

Explanations

words related to different industries (e.g., oil and gas industry, beverage industry)

oai_token-act-pair · gpt-3.5-turbo

mentions of various industries

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

tein

-0.85

pu

-0.79

bernatorial

-0.74

thood

-0.69

é£

-0.68

 Meier

-0.68

itial

-0.68

ypes

-0.67

forth

-0.66

Lar

-0.66

POSITIVE LOGITS

 titan

0.82

 mogul

0.79

eers

0.75

ONSORED

0.75

 lobby

0.74

 bailout

0.74

 industry

0.74

 professionals

0.74

 lobbying

0.74

 lobbyists

0.74

Activations Density 0.021%

words related to different industries (e.g., oil and gas industry, beverage industry)

mentions of various industries

No Comments

No Known Activations