INDEX

Explanations

responses or reactions to stimuli or events

oai_token-act-pair · gpt-3.5-turbo

parts of the word "responding"

oai_token-act-pair · gpt-4-turbo

occurrences of the term "responding" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

gling

-0.78

66666666

-0.74

 whispers

-0.72

 directions

-0.72

 devils

-0.69

 subt

-0.66

 Galileo

-0.65

BALL

-0.65

 caution

-0.65

POSITIVE LOGITS

onding

1.16

Resp

1.15

onds

1.07

awn

1.04

onder

0.94

responsive

0.92

rha

0.91

umph

0.90

awei

0.90

TPPStreamerBot

0.89

Activations Density 0.005%

responses or reactions to stimuli or events

parts of the word "responding"

occurrences of the term "responding" in various contexts

No Comments

No Known Activations