INDEX

Explanations

pairs of sentences where the second one continues from where the first one left off, creating a coherent paragraph

oai_token-act-pair · gpt-3.5-turbo

instances of violence or trauma

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 enriched

-0.98

 innov

-0.91

 persu

-0.91

 shrinking

-0.91

 persuasion

-0.90

 advant

-0.89

 quir

-0.85

 oppressed

-0.84

 striving

-0.84

 rebell

-0.84

POSITIVE LOGITS

Investigators

2.04

Police

2.01

Authorities

1.95

Officers

1.90

Detect

1.77

Officials

1.74

Witness

1.72

According

1.69

Prosecutors

1.67

Neigh

1.64

Activations Density 0.293%

pairs of sentences where the second one continues from where the first one left off, creating a coherent paragraph

instances of violence or trauma

No Comments

No Known Activations