INDEX

Explanations

adjectives used to describe significance or importance

oai_token-act-pair · gpt-3.5-turbo

significant nouns and adjectives related to political and social issues

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

rouse

-0.63

Judge

-0.62

Definition

-0.62

 Battlefield

-0.61

Shell

-0.59

 Prison

-0.58

Rh

-0.58

catch

-0.57

nings

-0.56

[+]

-0.56

POSITIVE LOGITS

=""

0.89

ï¸ı

0.77

bably

0.75

 Marketable

0.74

 pairs

0.73

iked

0.71

ngth

0.69

itled

0.69

uania

0.68

rahim

0.68

Activations Density 0.204%

adjectives used to describe significance or importance

significant nouns and adjectives related to political and social issues

No Comments

No Known Activations