INDEX

Explanations

instances of words related to legal and authoritative actions or decisions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "exercise" and its variations in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 slime

-0.63

 dump

-0.62

 fodder

-0.62

 Purdue

-0.62

azor

-0.61

 punch

-0.60

 statistic

-0.60

Jol

-0.59

 vomit

-0.58

 Anon

-0.58

POSITIVE LOGITS

orius

0.89

ĪĴ

0.84

 unfocusedRange

0.79

obe

0.78

 restraint

0.77

edience

0.76

rences

0.76

 strict

0.73

lesiastical

0.73

compliance

0.72

Activations Density 0.223%

instances of words related to legal and authoritative actions or decisions

occurrences of the word "exercise" and its variations in various contexts

No Comments

No Known Activations