INDEX

Explanations

names related to characters or places, identified through repetitions of words

oai_token-act-pair · gpt-3.5-turbo

references to the title "The Sound and the Fury."

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

pocket

-0.77

izational

-0.77

organic

-0.76

esthetic

-0.76

opathy

-0.75

kai

-0.74

mers

-0.74

quo

-0.73

repeat

-0.73

ership

-0.71

POSITIVE LOGITS

 Fury

0.97

anche

0.82

ricanes

0.80

 tremend

0.74

FC

0.73

rites

0.72

anches

0.71

ous

0.70

auld

0.69

raviolet

0.69

Activations Density 0.021%

names related to characters or places, identified through repetitions of words

references to the title "The Sound and the Fury."

No Comments

No Known Activations