INDEX

Explanations

words associated with justifying or providing reasons for actions or decisions

oai_token-act-pair · gpt-3.5-turbo

terms related to justification and rationale

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

berry

-0.78

grass

-0.76

ummer

-0.75

thumbnails

-0.74

semble

-0.72

along

-0.71

estone

-0.70

chron

-0.70

izen

-0.69

berries

-0.68

POSITIVE LOGITS

 justifying

0.93

why

0.85

 spending

0.77

 inaction

0.77

 justification

0.75

 attribut

0.74

 banning

0.71

 justify

0.71

ably

0.70

WHY

0.70

Activations Density 0.040%

words associated with justifying or providing reasons for actions or decisions

terms related to justification and rationale

No Comments

No Known Activations