INDEX

Explanations

events or actions related to decisions, outcomes, or consequences

oai_token-act-pair · gpt-3.5-turbo

verbs associated with official actions or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ivable

-0.68

ahime

-0.68

_>

-0.66

WHERE

-0.63

 equivalents

-0.63

 horm

-0.63

iner

-0.62

bilt

-0.62

 âĶľâĶĢâĶĢ

-0.61

#$#$

-0.60

POSITIVE LOGITS

 theirs

0.86

 unexpectedly

0.81

 abruptly

0.71

 hers

0.65

 prematurely

0.65

him

0.65

 mysteriously

0.64

 Schwe

0.62

 unsuccessfully

0.60

opsy

0.60

Activations Density 0.375%

events or actions related to decisions, outcomes, or consequences

verbs associated with official actions or decisions

No Comments

No Known Activations